Análisis de modelos SOM - Frecuencia datos de entrada: mes

Modelo

• ID: 334
• Descripción:
• Frecuencia: mes
• Variables: fecha_cnt, tmax, tmin, precip
• Dimensiones del mapa: 25,25
• Iteraciones: 10000
• Parámetros adicionales:

source("../../lib/som-utils.R")

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

source("../../lib/maps-utils.R")

Linking to GEOS 3.8.0, GDAL 3.0.4, PROJ 6.3.1

Carga del modelo desde disco

mpr.set_base_path_analysis()
model <- mpr.load_model("som-334.rds.xz")
summary(model)

SOM of size 25x25 with a hexagonal topology and a bubble neighbourhood function.
The number of data layers is 1.
Distance measure(s) used: sumofsquares.
Training data included: 94881 objects.
Mean distance to the closest unit in the map: 0.066.

plot(model, type="changes")

Carga del dataset de entrada

df <- mpr.load_data("datos_mes.csv.xz")

df

summary(df)

 id_estacion           fecha             fecha_cnt           tmax      
 Length:94881       Length:94881       Min.   : 1.000   Min.   :-53.0  
 Class :character   Class :character   1st Qu.: 4.000   1st Qu.:148.0  
 Mode  :character   Mode  :character   Median : 6.000   Median :198.0  
                                       Mean   : 6.497   Mean   :200.2  
                                       3rd Qu.: 9.000   3rd Qu.:255.0  
                                       Max.   :12.000   Max.   :403.0  
      tmin             precip           nevada           prof_nieve      
 Min.   :-121.00   Min.   :  0.00   Min.   :0.000000   Min.   :   0.000  
 1st Qu.:  53.00   1st Qu.:  3.00   1st Qu.:0.000000   1st Qu.:   0.000  
 Median :  98.00   Median : 10.00   Median :0.000000   Median :   0.000  
 Mean   :  98.86   Mean   : 16.25   Mean   :0.000295   Mean   :   0.467  
 3rd Qu.: 148.00   3rd Qu.: 22.00   3rd Qu.:0.000000   3rd Qu.:   0.000  
 Max.   : 254.00   Max.   :422.00   Max.   :6.000000   Max.   :1834.000  
    longitud        latitud            altitud      
 Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:38.28   1st Qu.: -5.6417   1st Qu.:  42.0  
 Median :40.82   Median : -3.4500   Median : 247.0  
 Mean   :39.66   Mean   : -3.4350   Mean   : 418.5  
 3rd Qu.:42.08   3rd Qu.:  0.4914   3rd Qu.: 656.0  
 Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

Carga de los mapas

world <- ne_countries(scale = "medium", returnclass = "sf")
spain <- subset(world, admin == "Spain")

Mapa de densidad

plot(model, type="count", shape = "straight", palette.name = mpr.degrade.bleu)

Número de elementos en cada celda:

nb <- table(model$unit.classif)
print(nb)

  1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17  18  19  20 
 93 148 187  56  76  62  56  54  33   9  56  21  12   8  10  16  51  21  46  49 
 21  22  23  24  25  26  27  28  29  30  31  32  33  34  35  36  37  38  39  40 
 56  52 121 183  53  95 143 218 252 225  40  87  82  66  36  41  64  16  11  17 
 41  42  43  44  45  46  47  48  49  50  51  52  53  54  55  56  57  58  59  60 
 56  83  79  53 183  69 107  94 195 151 144 184 212  66 172 102  58 103 171 106 
 61  62  63  64  65  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80 
 78  49  52  57  92 128 172 104  74 158  99 180 160 196 278 135 195 203 165 191 
 81  82  83  84  85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100 
155 120 129 113 157 138 138  63  56  54 107 135 200 153 162  93 161 178 262 275 
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 
213 229 191 217 221 224 161 190 116 101 141  96  87  37  75 113 154 182 182 219 
121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 
155 226 228 193 181 141 188 201 207 149 162  55 136  95 109 104  22 102  41  78 
141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 
118 123 103 151 159 128  89 243 222 222 199 214 206 194 146  73  67  79  42 103 
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 
112 115  50  53 134 115 124 179 118 185 213 180 232 177 136 202 193 159 184 222 
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 
170 133 102  52  84 112 138 108 102  67  72 138 137 133 163 183 179 194 206 157 
201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 
202 210 168 156 192  83 192 113 177 144 101 120  90  61 136 130 153 196 212 180 
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 
197 219 187 194 174 195 234 217 216 176 179 214 168 187 175 180 156 146 131  81 
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 
157 163  47 159 113 178 168 217 181 230 224 181 114 201 164 135 174 163  82 223 
261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 
200 195 154 106  81 176 218 164 183  73 105 128 147 111 235 144 201 188 158 133 
281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 
135 100 178 164  92  65 131 122 151 158 152 208 150 184 204 155  66 163 176 215 
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 
159 281 176 214 145 101  29 155 148 190 185 130 115 137 154 166  65 144 297 211 
321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 
156 197 116 230 164  56 192 215 166 155 176 154 182 151 145 151 144 130 176 155 
341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 
170 145 124 107 154 149 150 259 216 180 174 157 132 249 173 177 123 190 165 167 
361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 
217 163 121 137 154 101 146 182 186 224 101 219 105 174 114 131 246 126  80 232 
381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 
158 201 181 205 198 126 147 171 109  85  62 192 238 205 189 149 152 205 158 133 
401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 
174 176 233 136 185 197 234 218 217  88 133 177 129 143  96 138 172 178 171 143 
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 
167 206 181 129 132 259 144 152 240 190 220 159 196 227 227 143  71 109  68  83 
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 
 81  95 222 108 121 133 190 132 179  89 163 158 133 114 179 132 116 171 168 117 
461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 
 91 152 118 110 120 124 203 150 142 210 215 170 195 161 173 185 240 216 147 108 
481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 
163 133 121 248 210 137 132 140  90 144 100 159 164 175 114 184 178 198 134 169 
501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 
174 223 180 133 100  56 125 162 188 217 163  98  91 154 124 116  72 100  90 249 
521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 
173 199 164 264 178 201 166 145  94 182 142 136 134 119 168 179 158 197 159 150 
541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 
161  97 134 172 242 190 149 105 227 233 180 135 109 162 135 114 209 161 142 179 
561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 
192 228 182 183 215 112 132 251 225 128 179 151 187 171 139  93 118 218 168 172 
581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 
147 119  79 199 180 221 170 104 123 197 264 156  97 223 120 312 238 287 247 204 
601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 
 56 146 238 145 173 292 203 326 285 281 189 173 207 155 242 283 168 108 209 119 
621 622 623 624 625 
207 207 172 288 131 

Comprobación de nodos vacíos:

dim_model <- 25*25;
len_nb = length(nb);
empty_nodes <- dim_model != len_nb;
if (empty_nodes) {
  print(paste("[Warning] Existen nodos vacíos: ", len_nb, "/", dim_model))
}

Mapa de distancia entre vecinos

plot(model, type="dist.neighbours", shape = "straight")

Influencia de las variables

model_colnames = c("fecha_cnt", "tmax", "tmin", "precip")
model_ncol = length(model_colnames)

Mapa de variables.

plot(model, shape = "straight")

Mapa de calor por variable

par(mfrow=c(3,4))
for (j in 1:model_ncol) {
  plot(model, type="property", property=getCodes(model,1)[,j],
    palette.name=mpr.coolBlueHotRed,
    main=model_colnames[j],
    cex=0.5, shape = "straight")
}

Correlación para cada columna del vector de nodos

if (!empty_nodes) {
  cor <- apply(getCodes(model,1), 2, mpr.weighted.correlation, w=nb, som=model)
  print(cor)
}

       fecha_cnt      tmax      tmin       precip
[1,]  0.89870055 0.2873321 0.3315288 -0.005917268
[2,] -0.01723183 0.8228231 0.7840086 -0.542021548

Representación de cada variable en un mapa de factores:

if (!empty_nodes) {
  par(mfrow=c(1,1))
  plot(cor[1,], cor[2,], xlim=c(-1,1), ylim=c(-1,1), type="n")
  lines(c(-1,1),c(0,0))
  lines(c(0,0),c(-1,1))
  text(cor[1,], cor[2,], labels=model_colnames, cex=0.75)
  symbols(0,0,circles=1,inches=F,add=T)
}

Importancia de cada variable - varianza ponderada por el tamaño de la celda:

if (!empty_nodes) {
  sigma2 <- sqrt(apply(getCodes(model,1),2,function(x,effectif)
     {m<-sum(effectif*(x-weighted.mean(x,effectif))^2)/(sum(effectif)-1)},
     effectif=nb))
  print(sort(sigma2,decreasing=T))
}

fecha_cnt      tmax    precip      tmin 
0.9941955 0.9913372 0.9912748 0.9906302 

Clustering

if (!empty_nodes) {
  hac <- mpr.hac(model, nb)
}

Visualización de 3 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=3)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=3)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt           tmax            tmin             precip     
 Min.   : 1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.: 2.000   1st Qu.:130.0   1st Qu.:  33.00   1st Qu.: 5.00  
 Median : 4.000   Median :166.0   Median :  67.00   Median :12.00  
 Mean   : 5.668   Mean   :162.5   Mean   :  65.03   Mean   :15.41  
 3rd Qu.:10.000   3rd Qu.:198.0   3rd Qu.:  97.00   3rd Qu.:23.00  
 Max.   :12.000   Max.   :300.0   Max.   : 187.00   Max.   :98.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.95   1st Qu.: -5.5975  
 Median :0.000000   Median :   0.0000   Median :40.95   Median : -2.9553  
 Mean   :0.000486   Mean   :   0.3665   Mean   :40.03   Mean   : -3.1441  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.18   3rd Qu.:  0.4914  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  52.0  
 Median : 370.0  
 Mean   : 485.3  
 3rd Qu.: 704.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:118.0   1st Qu.:  48.00   1st Qu.: 57.00  
 Median : 9.000   Median :147.0   Median :  75.00   Median : 67.00  
 Mean   : 7.113   Mean   :145.4   Mean   :  72.18   Mean   : 74.74  
 3rd Qu.:11.000   3rd Qu.:184.0   3rd Qu.: 108.00   3rd Qu.: 84.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.82   1st Qu.: -7.860  
 Median :0   Median :   0.000   Median :42.44   Median : -3.831  
 Mean   :0   Mean   :   4.565   Mean   :41.44   Mean   : -3.987  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.: -1.033  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 176.0  
 Mean   : 474.5  
 3rd Qu.: 445.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:248.0   1st Qu.:141.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :275.0   Median :163.0   Median : 4.000   Median :0  
 Mean   : 7.882   Mean   :276.2   Mean   :163.6   Mean   : 8.559   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:301.0   3rd Qu.:187.0   3rd Qu.:13.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :64.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.99   Median : -3.5556   Median :  90.0  
 Mean   : 0.00286   Mean   :38.73   Mean   : -3.8687   Mean   : 290.3  
 3rd Qu.: 0.00000   3rd Qu.:41.63   3rd Qu.:  0.4914   3rd Qu.: 541.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

Visualización de 4 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=4)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=4)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:137.0   1st Qu.:  35.00   1st Qu.: 5.00  
 Median :3.000   Median :171.0   Median :  70.00   Median :12.00  
 Mean   :3.294   Mean   :168.7   Mean   :  68.46   Mean   :14.87  
 3rd Qu.:5.000   3rd Qu.:205.0   3rd Qu.: 102.00   3rd Qu.:22.00  
 Max.   :9.000   Max.   :300.0   Max.   : 187.00   Max.   :67.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.88   1st Qu.: -5.6156  
 Median :0.000000   Median :   0.0000   Median :40.95   Median : -3.4500  
 Mean   :0.000474   Mean   :   0.3901   Mean   :39.88   Mean   : -3.3430  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.18   3rd Qu.:  0.4731  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 286.0  
 Mean   : 450.9  
 3rd Qu.: 687.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:118.0   1st Qu.:  48.00   1st Qu.: 57.00  
 Median : 9.000   Median :147.0   Median :  75.00   Median : 67.00  
 Mean   : 7.113   Mean   :145.4   Mean   :  72.18   Mean   : 74.74  
 3rd Qu.:11.000   3rd Qu.:184.0   3rd Qu.: 108.00   3rd Qu.: 84.00  
 Max.   :12.000   Max.   :350.0   Max.   : 223.00   Max.   :422.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.82   1st Qu.: -7.860  
 Median :0   Median :   0.000   Median :42.44   Median : -3.831  
 Mean   :0   Mean   :   4.565   Mean   :41.44   Mean   : -3.987  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.: -1.033  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 176.0  
 Mean   : 474.5  
 3rd Qu.: 445.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.:116.0   1st Qu.:  29.00   1st Qu.: 5.00  
 Median :11.00   Median :153.0   Median :  60.00   Median :13.00  
 Mean   :11.09   Mean   :148.4   Mean   :  57.18   Mean   :16.64  
 3rd Qu.:12.00   3rd Qu.:184.0   3rd Qu.:  88.00   3rd Qu.:25.00  
 Max.   :12.00   Max.   :259.0   Max.   : 156.00   Max.   :98.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.48   1st Qu.: -4.8458  
 Median :0.0000000   Median :  0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.0005132   Mean   :  0.3124   Mean   :40.38   Mean   : -2.6896  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.:  0.5356  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  81  
 Median : 513  
 Mean   : 564  
 3rd Qu.: 788  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:248.0   1st Qu.:141.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :275.0   Median :163.0   Median : 4.000   Median :0  
 Mean   : 7.882   Mean   :276.2   Mean   :163.6   Mean   : 8.559   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:301.0   3rd Qu.:187.0   3rd Qu.:13.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :64.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.99   Median : -3.5556   Median :  90.0  
 Mean   : 0.00286   Mean   :38.73   Mean   : -3.8687   Mean   : 290.3  
 3rd Qu.: 0.00000   3rd Qu.:41.63   3rd Qu.:  0.4914   3rd Qu.: 541.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

Visualización de 5 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=5)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=5)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:2.000   1st Qu.:137.0   1st Qu.:  35.00   1st Qu.: 5.00  
 Median :3.000   Median :171.0   Median :  70.00   Median :12.00  
 Mean   :3.294   Mean   :168.7   Mean   :  68.46   Mean   :14.87  
 3rd Qu.:5.000   3rd Qu.:205.0   3rd Qu.: 102.00   3rd Qu.:22.00  
 Max.   :9.000   Max.   :300.0   Max.   : 187.00   Max.   :67.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:38.88   1st Qu.: -5.6156  
 Median :0.000000   Median :   0.0000   Median :40.95   Median : -3.4500  
 Mean   :0.000474   Mean   :   0.3901   Mean   :39.88   Mean   : -3.3430  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.18   3rd Qu.:  0.4731  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 286.0  
 Mean   : 450.9  
 3rd Qu.: 687.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:118.0   1st Qu.:  48.00   1st Qu.: 57.00  
 Median : 9.000   Median :147.0   Median :  75.00   Median : 67.00  
 Mean   : 7.129   Mean   :145.4   Mean   :  72.08   Mean   : 72.86  
 3rd Qu.:11.000   3rd Qu.:184.0   3rd Qu.: 108.00   3rd Qu.: 83.00  
 Max.   :12.000   Max.   :336.0   Max.   : 219.00   Max.   :190.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.82   1st Qu.: -7.456  
 Median :0   Median :   0.000   Median :42.44   Median : -3.831  
 Mean   :0   Mean   :   4.505   Mean   :41.45   Mean   : -3.948  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.: -0.558  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 158.0  
 Mean   : 475.5  
 3rd Qu.: 445.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :158.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:114.5   1st Qu.: 52.75   1st Qu.:177.0   1st Qu.:0  
 Median : 4.000   Median :131.5   Median : 75.00   Median :198.5   Median :0  
 Mean   : 5.926   Mean   :143.3   Mean   : 79.46   Mean   :213.0   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:228.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud       
 Min.   :  0.000   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.000   1st Qu.:41.67   1st Qu.: -8.624   1st Qu.:  94.03  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   :  8.971   Mean   :41.31   Mean   : -6.874   Mean   : 396.15  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -5.203   3rd Qu.: 370.00  
 Max.   :607.000   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.:116.0   1st Qu.:  29.00   1st Qu.: 5.00  
 Median :11.00   Median :153.0   Median :  60.00   Median :13.00  
 Mean   :11.09   Mean   :148.4   Mean   :  57.18   Mean   :16.64  
 3rd Qu.:12.00   3rd Qu.:184.0   3rd Qu.:  88.00   3rd Qu.:25.00  
 Max.   :12.00   Max.   :259.0   Max.   : 156.00   Max.   :98.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.48   1st Qu.: -4.8458  
 Median :0.0000000   Median :  0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.0005132   Mean   :  0.3124   Mean   :40.38   Mean   : -2.6896  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.:  0.5356  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  81  
 Median : 513  
 Mean   : 564  
 3rd Qu.: 788  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:248.0   1st Qu.:141.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :275.0   Median :163.0   Median : 4.000   Median :0  
 Mean   : 7.882   Mean   :276.2   Mean   :163.6   Mean   : 8.559   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:301.0   3rd Qu.:187.0   3rd Qu.:13.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :64.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.99   Median : -3.5556   Median :  90.0  
 Mean   : 0.00286   Mean   :38.73   Mean   : -3.8687   Mean   : 290.3  
 3rd Qu.: 0.00000   3rd Qu.:41.63   3rd Qu.:  0.4914   3rd Qu.: 541.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

Visualización de 6 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=6)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=6)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip     
 Min.   :1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.00  
 1st Qu.:1.000   1st Qu.:115.0   1st Qu.:  17.00   1st Qu.: 5.00  
 Median :2.000   Median :145.0   Median :  42.00   Median :13.00  
 Mean   :2.432   Mean   :139.7   Mean   :  41.82   Mean   :17.22  
 3rd Qu.:3.000   3rd Qu.:167.0   3rd Qu.:  67.00   3rd Qu.:27.00  
 Max.   :7.000   Max.   :250.0   Max.   : 179.00   Max.   :67.00  
     nevada           prof_nieve           longitud        latitud        
 Min.   :0.000000   Min.   :   0.0000   Min.   :27.82   Min.   :-17.8889  
 1st Qu.:0.000000   1st Qu.:   0.0000   1st Qu.:39.49   1st Qu.: -4.8500  
 Median :0.000000   Median :   0.0000   Median :41.11   Median : -2.7331  
 Mean   :0.000805   Mean   :   0.6446   Mean   :40.43   Mean   : -2.8312  
 3rd Qu.:0.000000   3rd Qu.:   0.0000   3rd Qu.:42.24   3rd Qu.:  0.4914  
 Max.   :6.000000   Max.   :1494.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  71.0  
 Median : 445.0  
 Mean   : 519.3  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt           tmax            tmin             precip      
 Min.   : 1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00  
 1st Qu.: 3.000   1st Qu.:118.0   1st Qu.:  48.00   1st Qu.: 57.00  
 Median : 9.000   Median :147.0   Median :  75.00   Median : 67.00  
 Mean   : 7.129   Mean   :145.4   Mean   :  72.08   Mean   : 72.86  
 3rd Qu.:11.000   3rd Qu.:184.0   3rd Qu.: 108.00   3rd Qu.: 83.00  
 Max.   :12.000   Max.   :336.0   Max.   : 219.00   Max.   :190.00  
     nevada    prof_nieve          longitud        latitud       
 Min.   :0   Min.   :   0.000   Min.   :27.82   Min.   :-17.889  
 1st Qu.:0   1st Qu.:   0.000   1st Qu.:40.82   1st Qu.: -7.456  
 Median :0   Median :   0.000   Median :42.44   Median : -3.831  
 Mean   :0   Mean   :   4.505   Mean   :41.45   Mean   : -3.948  
 3rd Qu.:0   3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.: -0.558  
 Max.   :0   Max.   :1834.000   Max.   :43.57   Max.   :  4.216  
    altitud      
 Min.   :   1.0  
 1st Qu.:  42.0  
 Median : 158.0  
 Mean   : 475.5  
 3rd Qu.: 445.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :158.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:114.5   1st Qu.: 52.75   1st Qu.:177.0   1st Qu.:0  
 Median : 4.000   Median :131.5   Median : 75.00   Median :198.5   Median :0  
 Mean   : 5.926   Mean   :143.3   Mean   : 79.46   Mean   :213.0   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:228.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud       
 Min.   :  0.000   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.000   1st Qu.:41.67   1st Qu.: -8.624   1st Qu.:  94.03  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   :  8.971   Mean   :41.31   Mean   : -6.874   Mean   : 396.15  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -5.203   3rd Qu.: 370.00  
 Max.   :607.000   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.:116.0   1st Qu.:  29.00   1st Qu.: 5.00  
 Median :11.00   Median :153.0   Median :  60.00   Median :13.00  
 Mean   :11.09   Mean   :148.4   Mean   :  57.18   Mean   :16.64  
 3rd Qu.:12.00   3rd Qu.:184.0   3rd Qu.:  88.00   3rd Qu.:25.00  
 Max.   :12.00   Max.   :259.0   Max.   : 156.00   Max.   :98.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.48   1st Qu.: -4.8458  
 Median :0.0000000   Median :  0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.0005132   Mean   :  0.3124   Mean   :40.38   Mean   : -2.6896  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.:  0.5356  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  81  
 Median : 513  
 Mean   : 564  
 3rd Qu.: 788  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:248.0   1st Qu.:141.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :275.0   Median :163.0   Median : 4.000   Median :0  
 Mean   : 7.882   Mean   :276.2   Mean   :163.6   Mean   : 8.559   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:301.0   3rd Qu.:187.0   3rd Qu.:13.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :64.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.99   Median : -3.5556   Median :  90.0  
 Mean   : 0.00286   Mean   :38.73   Mean   : -3.8687   Mean   : 290.3  
 3rd Qu.: 0.00000   3rd Qu.:41.63   3rd Qu.:  0.4914   3rd Qu.: 541.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 25.0   Min.   : 0.00   Min.   :0  
 1st Qu.:4.000   1st Qu.:191.0   1st Qu.: 85.0   1st Qu.: 4.00   1st Qu.:0  
 Median :5.000   Median :210.0   Median :106.0   Median :11.00   Median :0  
 Mean   :4.529   Mean   :210.2   Mean   :106.6   Mean   :11.51   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:230.0   3rd Qu.:127.0   3rd Qu.:18.00   3rd Qu.:0  
 Max.   :9.000   Max.   :300.0   Max.   :187.0   Max.   :44.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud       
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.00  
 1st Qu.: 0.00000   1st Qu.:37.42   1st Qu.: -5.8792   1st Qu.:  32.00  
 Median : 0.00000   Median :40.48   Median : -3.7642   Median :  93.05  
 Mean   : 0.02538   Mean   :39.08   Mean   : -4.0764   Mean   : 352.92  
 3rd Qu.: 0.00000   3rd Qu.:42.01   3rd Qu.:  0.3664   3rd Qu.: 609.00  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

Visualización de 8 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=8)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=8)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip      
 Min.   :1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.000  
 1st Qu.:1.000   1st Qu.:113.0   1st Qu.:  11.00   1st Qu.: 3.000  
 Median :2.000   Median :142.0   Median :  36.00   Median : 8.000  
 Mean   :2.104   Mean   :136.6   Mean   :  33.33   Mean   : 9.272  
 3rd Qu.:3.000   3rd Qu.:164.0   3rd Qu.:  56.00   3rd Qu.:14.000  
 Max.   :7.000   Max.   :250.0   Max.   : 134.00   Max.   :35.000  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:39.47   1st Qu.: -4.6800  
 Median :0.000000   Median :  0.0000   Median :40.95   Median : -2.3308  
 Mean   :0.001159   Mean   :  0.4289   Mean   :40.28   Mean   : -2.4952  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.77   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :626.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  81.0  
 Median : 513.0  
 Mean   : 519.2  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00   Min.   :0  
 1st Qu.:1.000   1st Qu.: 84.0   1st Qu.:  13.00   1st Qu.: 57.00   1st Qu.:0  
 Median :2.000   Median :125.0   Median :  52.00   Median : 67.00   Median :0  
 Mean   :2.703   Mean   :111.8   Mean   :  40.03   Mean   : 70.94   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:149.0   3rd Qu.:  74.00   3rd Qu.: 81.00   3rd Qu.:0  
 Max.   :8.000   Max.   :250.0   Max.   : 172.00   Max.   :155.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :   0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:41.98   1st Qu.: -7.8631   1st Qu.:  64.0  
 Median :   0.000   Median :42.53   Median : -3.8189   Median : 261.0  
 Mean   :   9.989   Mean   :41.81   Mean   : -3.6945   Mean   : 743.8  
 3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.:  0.7317   3rd Qu.:1894.0  
 Max.   :1834.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :158.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:114.5   1st Qu.: 52.75   1st Qu.:177.0   1st Qu.:0  
 Median : 4.000   Median :131.5   Median : 75.00   Median :198.5   Median :0  
 Mean   : 5.926   Mean   :143.3   Mean   : 79.46   Mean   :213.0   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:228.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud       
 Min.   :  0.000   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.000   1st Qu.:41.67   1st Qu.: -8.624   1st Qu.:  94.03  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   :  8.971   Mean   :41.31   Mean   : -6.874   Mean   : 396.15  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -5.203   3rd Qu.: 370.00  
 Max.   :607.000   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 5.00   Min.   : -8.0   Min.   :-58.00   Min.   : 43.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:139.0   1st Qu.: 71.00   1st Qu.: 57.00   1st Qu.:0  
 Median :11.00   Median :170.0   Median : 96.00   Median : 66.00   Median :0  
 Mean   :10.61   Mean   :171.8   Mean   : 97.27   Mean   : 74.36   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:201.0   3rd Qu.:124.00   3rd Qu.: 85.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.00   Max.   :190.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   : 0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:40.38   1st Qu.: -7.456   1st Qu.:  32.0  
 Median : 0.0000   Median :42.38   Median : -3.831   Median :  98.0  
 Mean   : 0.1946   Mean   :41.16   Mean   : -4.147   Mean   : 264.7  
 3rd Qu.: 0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 351.0  
 Max.   :81.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax            tmin             precip     
 Min.   : 7.00   Min.   :-24.0   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.:116.0   1st Qu.:  29.00   1st Qu.: 5.00  
 Median :11.00   Median :153.0   Median :  60.00   Median :13.00  
 Mean   :11.09   Mean   :148.4   Mean   :  57.18   Mean   :16.64  
 3rd Qu.:12.00   3rd Qu.:184.0   3rd Qu.:  88.00   3rd Qu.:25.00  
 Max.   :12.00   Max.   :259.0   Max.   : 156.00   Max.   :98.00  
     nevada            prof_nieve          longitud        latitud        
 Min.   :0.0000000   Min.   :  0.0000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0000000   1st Qu.:  0.0000   1st Qu.:39.48   1st Qu.: -4.8458  
 Median :0.0000000   Median :  0.0000   Median :40.96   Median : -2.4831  
 Mean   :0.0005132   Mean   :  0.3124   Mean   :40.38   Mean   : -2.6896  
 3rd Qu.:0.0000000   3rd Qu.:  0.0000   3rd Qu.:42.14   3rd Qu.:  0.5356  
 Max.   :3.0000000   Max.   :382.0000   Max.   :43.57   Max.   :  4.2156  
    altitud    
 Min.   :   1  
 1st Qu.:  81  
 Median : 513  
 Mean   : 564  
 3rd Qu.: 788  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   :1.000   Min.   : 14.0   Min.   :-58.00   Min.   :14.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:119.0   1st Qu.: 33.00   1st Qu.:28.00   1st Qu.:0  
 Median :3.000   Median :151.0   Median : 63.00   Median :34.00   Median :0  
 Mean   :3.176   Mean   :146.7   Mean   : 61.08   Mean   :35.27   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:176.0   3rd Qu.: 88.00   3rd Qu.:42.00   3rd Qu.:0  
 Max.   :7.000   Max.   :250.0   Max.   :179.00   Max.   :67.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :   0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:40.38   1st Qu.: -5.8728   1st Qu.:  58.0  
 Median :   0.000   Median :41.96   Median : -3.7642   Median : 370.0  
 Mean   :   1.135   Mean   :40.77   Mean   : -3.5942   Mean   : 519.3  
 3rd Qu.:   0.000   3rd Qu.:42.87   3rd Qu.:  0.3056   3rd Qu.: 775.0  
 Max.   :1494.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt           tmax            tmin           precip           nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.000   1st Qu.:248.0   1st Qu.:141.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.000   Median :275.0   Median :163.0   Median : 4.000   Median :0  
 Mean   : 7.882   Mean   :276.2   Mean   :163.6   Mean   : 8.559   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:301.0   3rd Qu.:187.0   3rd Qu.:13.000   3rd Qu.:0  
 Max.   :12.000   Max.   :403.0   Max.   :254.0   Max.   :64.000   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.26   1st Qu.: -5.8728   1st Qu.:  32.0  
 Median : 0.00000   Median :39.99   Median : -3.5556   Median :  90.0  
 Mean   : 0.00286   Mean   :38.73   Mean   : -3.8687   Mean   : 290.3  
 3rd Qu.: 0.00000   3rd Qu.:41.63   3rd Qu.:  0.4914   3rd Qu.: 541.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 25.0   Min.   : 0.00   Min.   :0  
 1st Qu.:4.000   1st Qu.:191.0   1st Qu.: 85.0   1st Qu.: 4.00   1st Qu.:0  
 Median :5.000   Median :210.0   Median :106.0   Median :11.00   Median :0  
 Mean   :4.529   Mean   :210.2   Mean   :106.6   Mean   :11.51   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:230.0   3rd Qu.:127.0   3rd Qu.:18.00   3rd Qu.:0  
 Max.   :9.000   Max.   :300.0   Max.   :187.0   Max.   :44.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud       
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.00  
 1st Qu.: 0.00000   1st Qu.:37.42   1st Qu.: -5.8792   1st Qu.:  32.00  
 Median : 0.00000   Median :40.48   Median : -3.7642   Median :  93.05  
 Mean   : 0.02538   Mean   :39.08   Mean   : -4.0764   Mean   : 352.92  
 3rd Qu.: 0.00000   3rd Qu.:42.01   3rd Qu.:  0.3664   3rd Qu.: 609.00  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.00  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

Visualización de 10 clústeres:

if (!empty_nodes) {
  plot(hac, hang=-1, labels=F)
  rect.hclust(hac, k=10)
}

Visualización de los clústers en el mapa

A qué clúster pertenece cada nodo del mapa de kohonen:

if (!empty_nodes) {
  groups <- cutree(hac, k=10)
  plot(model, type="mapping",
    bgcol=c("steelblue1","sienna1","yellowgreen","red","blue","yellow","purple","green","white","#1f77b4", '#ff7f0e', '#2ca02c', '#d62728', '#9467bd', '#8c564b', '#e377c2')[groups],
    shape = "straight", labels = "")
  add.cluster.boundaries(model, clustering=groups)
}

Análisis de las observaciones de cada cluster

if (!empty_nodes) {
  # Asignamos a cada registro su clúster
  df$cluster <- groups[model$unit.classif]
}

Nuevos dataframes por cluster

if (!empty_nodes) {
  # Creo nuevos dataframes, uno por cada clúster.
  df.cluster01 <- subset(df, cluster==1)
  df.cluster02 <- subset(df, cluster==2)
  df.cluster03 <- subset(df, cluster==3)
  df.cluster04 <- subset(df, cluster==4)
  df.cluster05 <- subset(df, cluster==5)
  df.cluster06 <- subset(df, cluster==6)
  df.cluster07 <- subset(df, cluster==7)
  df.cluster08 <- subset(df, cluster==8)
  df.cluster09 <- subset(df, cluster==9)
  df.cluster10 <- subset(df, cluster==10)

  # Extraigo del dataframe las features.
  df.cluster01 <- select(df.cluster01, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster02 <- select(df.cluster02, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster03 <- select(df.cluster03, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster04 <- select(df.cluster04, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster05 <- select(df.cluster05, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster06 <- select(df.cluster06, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster07 <- select(df.cluster07, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster08 <- select(df.cluster08, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster09 <- select(df.cluster09, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
  df.cluster10 <- select(df.cluster10, fecha_cnt, tmax, tmin, precip, nevada, prof_nieve, longitud, latitud, altitud)
}

if (!empty_nodes) summary(df.cluster01)

   fecha_cnt          tmax            tmin             precip      
 Min.   :1.000   Min.   :-46.0   Min.   :-121.00   Min.   : 0.000  
 1st Qu.:1.000   1st Qu.:113.0   1st Qu.:  11.00   1st Qu.: 3.000  
 Median :2.000   Median :142.0   Median :  36.00   Median : 8.000  
 Mean   :2.104   Mean   :136.6   Mean   :  33.33   Mean   : 9.272  
 3rd Qu.:3.000   3rd Qu.:164.0   3rd Qu.:  56.00   3rd Qu.:14.000  
 Max.   :7.000   Max.   :250.0   Max.   : 134.00   Max.   :35.000  
     nevada           prof_nieve          longitud        latitud        
 Min.   :0.000000   Min.   :  0.0000   Min.   :28.31   Min.   :-16.4992  
 1st Qu.:0.000000   1st Qu.:  0.0000   1st Qu.:39.47   1st Qu.: -4.6800  
 Median :0.000000   Median :  0.0000   Median :40.95   Median : -2.3308  
 Mean   :0.001159   Mean   :  0.4289   Mean   :40.28   Mean   : -2.4952  
 3rd Qu.:0.000000   3rd Qu.:  0.0000   3rd Qu.:41.77   3rd Qu.:  0.4942  
 Max.   :6.000000   Max.   :626.0000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  81.0  
 Median : 513.0  
 Mean   : 519.2  
 3rd Qu.: 779.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster02)

   fecha_cnt          tmax            tmin             precip           nevada 
 Min.   :1.000   Min.   :-53.0   Min.   :-115.00   Min.   : 23.00   Min.   :0  
 1st Qu.:1.000   1st Qu.: 84.0   1st Qu.:  13.00   1st Qu.: 57.00   1st Qu.:0  
 Median :2.000   Median :125.0   Median :  52.00   Median : 67.00   Median :0  
 Mean   :2.703   Mean   :111.8   Mean   :  40.03   Mean   : 70.94   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:149.0   3rd Qu.:  74.00   3rd Qu.: 81.00   3rd Qu.:0  
 Max.   :8.000   Max.   :250.0   Max.   : 172.00   Max.   :155.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :   0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:41.98   1st Qu.: -7.8631   1st Qu.:  64.0  
 Median :   0.000   Median :42.53   Median : -3.8189   Median : 261.0  
 Mean   :   9.989   Mean   :41.81   Mean   : -3.6945   Mean   : 743.8  
 3rd Qu.:   0.000   3rd Qu.:43.31   3rd Qu.:  0.7317   3rd Qu.:1894.0  
 Max.   :1834.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster03)

   fecha_cnt           tmax            tmin            precip          nevada 
 Min.   : 1.000   Min.   : 11.0   Min.   :-27.00   Min.   :158.0   Min.   :0  
 1st Qu.: 2.000   1st Qu.:114.5   1st Qu.: 52.75   1st Qu.:177.0   1st Qu.:0  
 Median : 4.000   Median :131.5   Median : 75.00   Median :198.5   Median :0  
 Mean   : 5.926   Mean   :143.3   Mean   : 79.46   Mean   :213.0   Mean   :0  
 3rd Qu.:11.000   3rd Qu.:151.0   3rd Qu.: 92.00   3rd Qu.:228.5   3rd Qu.:0  
 Max.   :12.000   Max.   :350.0   Max.   :223.00   Max.   :422.0   Max.   :0  
   prof_nieve         longitud        latitud           altitud       
 Min.   :  0.000   Min.   :28.31   Min.   :-16.499   Min.   :   4.00  
 1st Qu.:  0.000   1st Qu.:41.67   1st Qu.: -8.624   1st Qu.:  94.03  
 Median :  0.000   Median :42.24   Median : -8.411   Median : 261.00  
 Mean   :  8.971   Mean   :41.31   Mean   : -6.874   Mean   : 396.15  
 3rd Qu.:  0.000   3rd Qu.:42.89   3rd Qu.: -5.203   3rd Qu.: 370.00  
 Max.   :607.000   Max.   :43.36   Max.   :  2.825   Max.   :2371.00  

if (!empty_nodes) summary(df.cluster04)

   fecha_cnt          tmax            tmin            precip           nevada 
 Min.   : 5.00   Min.   : -8.0   Min.   :-58.00   Min.   : 43.00   Min.   :0  
 1st Qu.:10.00   1st Qu.:139.0   1st Qu.: 71.00   1st Qu.: 57.00   1st Qu.:0  
 Median :11.00   Median :170.0   Median : 96.00   Median : 66.00   Median :0  
 Mean   :10.61   Mean   :171.8   Mean   : 97.27   Mean   : 74.36   Mean   :0  
 3rd Qu.:11.00   3rd Qu.:201.0   3rd Qu.:124.00   3rd Qu.: 85.00   3rd Qu.:0  
 Max.   :12.00   Max.   :336.0   Max.   :219.00   Max.   :190.00   Max.   :0  
   prof_nieve         longitud        latitud           altitud      
 Min.   : 0.0000   Min.   :27.82   Min.   :-17.889   Min.   :   1.0  
 1st Qu.: 0.0000   1st Qu.:40.38   1st Qu.: -7.456   1st Qu.:  32.0  
 Median : 0.0000   Median :42.38   Median : -3.831   Median :  98.0  
 Mean   : 0.1946   Mean   :41.16   Mean   : -4.147   Mean   : 264.7  
 3rd Qu.: 0.0000   3rd Qu.:43.31   3rd Qu.: -1.787   3rd Qu.: 351.0  
 Max.   :81.0000   Max.   :43.57   Max.   :  4.216   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster05)

   fecha_cnt          tmax             tmin             precip     
 Min.   : 8.00   Min.   :-24.00   Min.   :-110.00   Min.   : 0.00  
 1st Qu.:11.00   1st Qu.: 79.00   1st Qu.:  -5.00   1st Qu.:11.00  
 Median :12.00   Median :100.00   Median :  15.00   Median :20.00  
 Mean   :11.52   Mean   : 96.13   Mean   :  14.12   Mean   :21.74  
 3rd Qu.:12.00   3rd Qu.:117.00   3rd Qu.:  36.00   3rd Qu.:30.00  
 Max.   :12.00   Max.   :166.00   Max.   :  82.00   Max.   :98.00  
     nevada           prof_nieve         longitud        latitud       
 Min.   :0.000000   Min.   :  0.000   Min.   :28.31   Min.   :-16.499  
 1st Qu.:0.000000   1st Qu.:  0.000   1st Qu.:40.66   1st Qu.: -4.535  
 Median :0.000000   Median :  0.000   Median :41.65   Median : -2.733  
 Mean   :0.001699   Mean   :  1.052   Mean   :41.13   Mean   : -2.685  
 3rd Qu.:0.000000   3rd Qu.:  0.000   3rd Qu.:42.43   3rd Qu.:  0.595  
 Max.   :3.000000   Max.   :382.000   Max.   :43.57   Max.   :  4.216  
    altitud    
 Min.   :   1  
 1st Qu.: 540  
 Median : 779  
 Mean   : 945  
 3rd Qu.:1056  
 Max.   :2535  

if (!empty_nodes) summary(df.cluster06)

   fecha_cnt          tmax            tmin            precip          nevada 
 Min.   :1.000   Min.   : 14.0   Min.   :-58.00   Min.   :14.00   Min.   :0  
 1st Qu.:2.000   1st Qu.:119.0   1st Qu.: 33.00   1st Qu.:28.00   1st Qu.:0  
 Median :3.000   Median :151.0   Median : 63.00   Median :34.00   Median :0  
 Mean   :3.176   Mean   :146.7   Mean   : 61.08   Mean   :35.27   Mean   :0  
 3rd Qu.:4.000   3rd Qu.:176.0   3rd Qu.: 88.00   3rd Qu.:42.00   3rd Qu.:0  
 Max.   :7.000   Max.   :250.0   Max.   :179.00   Max.   :67.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   :   0.000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:   0.000   1st Qu.:40.38   1st Qu.: -5.8728   1st Qu.:  58.0  
 Median :   0.000   Median :41.96   Median : -3.7642   Median : 370.0  
 Mean   :   1.135   Mean   :40.77   Mean   : -3.5942   Mean   : 519.3  
 3rd Qu.:   0.000   3rd Qu.:42.87   3rd Qu.:  0.3056   3rd Qu.: 775.0  
 Max.   :1494.000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.0  

if (!empty_nodes) summary(df.cluster07)

   fecha_cnt          tmax            tmin            precip     
 Min.   : 7.00   Min.   : 57.0   Min.   :-35.00   Min.   : 0.00  
 1st Qu.:10.00   1st Qu.:146.0   1st Qu.: 52.00   1st Qu.: 4.00  
 Median :11.00   Median :170.0   Median : 75.00   Median :11.00  
 Mean   :10.94   Mean   :167.6   Mean   : 72.98   Mean   :14.77  
 3rd Qu.:12.00   3rd Qu.:192.0   3rd Qu.: 96.00   3rd Qu.:22.00  
 Max.   :12.00   Max.   :259.0   Max.   :156.00   Max.   :57.00  
     nevada          prof_nieve          longitud        latitud        
 Min.   :0.0e+00   Min.   : 0.00000   Min.   :27.92   Min.   :-17.7550  
 1st Qu.:0.0e+00   1st Qu.: 0.00000   1st Qu.:38.88   1st Qu.: -5.2892  
 Median :0.0e+00   Median : 0.00000   Median :40.87   Median : -2.4544  
 Mean   :7.8e-05   Mean   : 0.04093   Mean   :40.11   Mean   : -2.6910  
 3rd Qu.:0.0e+00   3rd Qu.: 0.00000   3rd Qu.:41.98   3rd Qu.:  0.4942  
 Max.   :1.0e+00   Max.   :59.00000   Max.   :43.57   Max.   :  4.2156  
    altitud      
 Min.   :   1.0  
 1st Qu.:  44.0  
 Median : 252.0  
 Mean   : 424.1  
 3rd Qu.: 667.0  
 Max.   :2535.0  

if (!empty_nodes) summary(df.cluster08)

   fecha_cnt           tmax            tmin           precip          nevada 
 Min.   : 4.000   Min.   :180.0   Min.   : 54.0   Min.   : 0.00   Min.   :0  
 1st Qu.: 6.000   1st Qu.:235.0   1st Qu.:130.0   1st Qu.: 2.00   1st Qu.:0  
 Median : 8.000   Median :256.0   Median :149.0   Median : 9.00   Median :0  
 Mean   : 8.028   Mean   :256.2   Mean   :147.9   Mean   :12.37   Mean   :0  
 3rd Qu.: 9.000   3rd Qu.:276.0   3rd Qu.:166.0   3rd Qu.:19.00   3rd Qu.:0  
 Max.   :12.000   Max.   :352.0   Max.   :244.0   Max.   :64.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud      
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.: 0.00000   1st Qu.:37.79   1st Qu.: -5.8792   1st Qu.:  33.0  
 Median : 0.00000   Median :40.82   Median : -3.6325   Median : 108.0  
 Mean   : 0.00473   Mean   :39.14   Mean   : -4.0041   Mean   : 323.6  
 3rd Qu.: 0.00000   3rd Qu.:42.05   3rd Qu.:  0.4731   3rd Qu.: 609.0  
 Max.   :35.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2371.0  

if (!empty_nodes) summary(df.cluster09)

   fecha_cnt          tmax            tmin           precip          nevada 
 Min.   :1.000   Min.   : 87.0   Min.   : 25.0   Min.   : 0.00   Min.   :0  
 1st Qu.:4.000   1st Qu.:191.0   1st Qu.: 85.0   1st Qu.: 4.00   1st Qu.:0  
 Median :5.000   Median :210.0   Median :106.0   Median :11.00   Median :0  
 Mean   :4.529   Mean   :210.2   Mean   :106.6   Mean   :11.51   Mean   :0  
 3rd Qu.:5.000   3rd Qu.:230.0   3rd Qu.:127.0   3rd Qu.:18.00   3rd Qu.:0  
 Max.   :9.000   Max.   :300.0   Max.   :187.0   Max.   :44.00   Max.   :0  
   prof_nieve          longitud        latitud            altitud       
 Min.   : 0.00000   Min.   :27.82   Min.   :-17.8889   Min.   :   1.00  
 1st Qu.: 0.00000   1st Qu.:37.42   1st Qu.: -5.8792   1st Qu.:  32.00  
 Median : 0.00000   Median :40.48   Median : -3.7642   Median :  93.05  
 Mean   : 0.02538   Mean   :39.08   Mean   : -4.0764   Mean   : 352.92  
 3rd Qu.: 0.00000   3rd Qu.:42.01   3rd Qu.:  0.3664   3rd Qu.: 609.00  
 Max.   :38.00000   Max.   :43.57   Max.   :  4.2156   Max.   :2535.00  

if (!empty_nodes) summary(df.cluster10)

   fecha_cnt          tmax            tmin           precip           nevada 
 Min.   : 5.00   Min.   :217.0   Min.   :112.0   Min.   : 0.000   Min.   :0  
 1st Qu.: 7.00   1st Qu.:288.0   1st Qu.:170.0   1st Qu.: 0.000   1st Qu.:0  
 Median : 8.00   Median :306.0   Median :189.0   Median : 1.000   Median :0  
 Mean   : 7.66   Mean   :306.6   Mean   :187.5   Mean   : 2.753   Mean   :0  
 3rd Qu.: 8.00   3rd Qu.:325.0   3rd Qu.:206.0   3rd Qu.: 4.000   3rd Qu.:0  
 Max.   :11.00   Max.   :403.0   Max.   :254.0   Max.   :28.000   Max.   :0  
   prof_nieve    longitud        latitud            altitud      
 Min.   :0    Min.   :27.82   Min.   :-17.8889   Min.   :   1.0  
 1st Qu.:0    1st Qu.:37.18   1st Qu.: -5.6492   1st Qu.:  27.0  
 Median :0    Median :38.95   Median : -3.4503   Median :  81.0  
 Mean   :0    Mean   :38.10   Mean   : -3.6625   Mean   : 239.6  
 3rd Qu.:0    3rd Qu.:40.82   3rd Qu.:  0.4914   3rd Qu.: 515.0  
 Max.   :0    Max.   :43.56   Max.   :  4.2156   Max.   :1167.0  

Número de elementos en cada clúster

if (!empty_nodes) {
  df.clusters.dim <- c(dim(df.cluster01)[1], dim(df.cluster02)[1], dim(df.cluster03)[1], dim(df.cluster04)[1], dim(df.cluster05)[1], dim(df.cluster06)[1], dim(df.cluster07)[1], dim(df.cluster08)[1], dim(df.cluster09)[1], dim(df.cluster10)[1])
  barplot(df.clusters.dim,
          names.arg = c("cluster01", "cluster02", "cluster03", "cluster04", "cluster05", "cluster06", "cluster07", "cluster08", "cluster09", "cluster10"),
          col = "steelblue1")
}

Distribución de los datos

if (!empty_nodes) mpr.hist(df.cluster01)

if (!empty_nodes) mpr.hist(df.cluster02)

if (!empty_nodes) mpr.hist(df.cluster03)

if (!empty_nodes) mpr.hist(df.cluster04)

if (!empty_nodes) mpr.hist(df.cluster05)

if (!empty_nodes) mpr.hist(df.cluster06)

if (!empty_nodes) mpr.hist(df.cluster07)

if (!empty_nodes) mpr.hist(df.cluster08)

if (!empty_nodes) mpr.hist(df.cluster09)

if (!empty_nodes) mpr.hist(df.cluster10)

if (!empty_nodes) mpr.boxplot(df.cluster01)
if (!empty_nodes) mpr.boxplot(df.cluster02)

if (!empty_nodes) mpr.boxplot(df.cluster03)

if (!empty_nodes) mpr.boxplot(df.cluster04)

if (!empty_nodes) mpr.boxplot(df.cluster05)

if (!empty_nodes) mpr.boxplot(df.cluster06)

if (!empty_nodes) mpr.boxplot(df.cluster07)

if (!empty_nodes) mpr.boxplot(df.cluster08)

if (!empty_nodes) mpr.boxplot(df.cluster09)

if (!empty_nodes) mpr.boxplot(df.cluster10)

Localización geográfica de las estaciones de medida de cada cluster

# Agrupa por longitud y latitud para rellenar el mapa con menos datos.
if (!empty_nodes) {
  df.cluster01.grouped <- mpr.group_by_geo(df.cluster01)
  df.cluster02.grouped <- mpr.group_by_geo(df.cluster02)
  df.cluster03.grouped <- mpr.group_by_geo(df.cluster03)
  df.cluster04.grouped <- mpr.group_by_geo(df.cluster04)
  df.cluster05.grouped <- mpr.group_by_geo(df.cluster05)
  df.cluster06.grouped <- mpr.group_by_geo(df.cluster06)
  df.cluster07.grouped <- mpr.group_by_geo(df.cluster07)
  df.cluster08.grouped <- mpr.group_by_geo(df.cluster08)
  df.cluster09.grouped <- mpr.group_by_geo(df.cluster09)
  df.cluster10.grouped <- mpr.group_by_geo(df.cluster10)
}

if (!empty_nodes) mpr.draw_map(spain, df.cluster01.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster02.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster03.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster04.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster05.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster06.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster07.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster08.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster09.grouped)

if (!empty_nodes) mpr.draw_map(spain, df.cluster10.grouped)